研究发现 AI 代理在文档拉取请求中比人类更活跃，且其文档修改较少被人类跟进，引发对文档质量和人机协作的担忧。
摘要：
随着软件工程向 SE3.0 进展，AI 代理越来越多地被用来执行开发任务并为软件项目贡献更改。因此，了解这些贡献的程度以及人类开发者如何审查和介入至关重要，因为这些因素影响着将工作委托给 AI 代理的风险。尽管最近的研究已考察了 AI 代理如何支持软件开发任务（例如代码生成、问题解决和 PR 自动化），但它们在文档任务中的作用仍被忽视，尽管文档被广泛消费，并影响开发者对软件的理解和使用方式。使用 AIDev，我们分析了 1,997 个由 AI 代理和人类开发者撰写的文档相关拉取请求（PR），其中文档 PR 是那些创建或修改项目文档 artifacts 的请求。我们发现，AI 代理提交的文档相关 PR 比人类多得多。我们进一步观察到，代理撰写的文档编辑通常被整合，而人类很少进行后续修改，这引发了对审查实践和代理生成文档可靠性的担忧。总体而言，尽管 AI 代理已对文档工作流程做出了显著贡献，但我们的结果表明，对于 SE3.0 中文档质量保证和人机协作的新兴挑战存在担忧。
英文摘要：
As software engineering moves toward SE3.0, AI agents are increasingly used to carry out development tasks and contribute changes to software projects. It is therefore important to understand the extent of these contributions and how human developers review and intervene, since these factors shape the risks of delegating work to AI agents. While recent studies have examined how AI agents support software development tasks (e.g., code generation, issue resolution, and PR automation), their role in documentation tasks remains underexplored-even though documentation is widely consumed and shapes how developers understand and use software.
Using the AIDev, we analyze 1,997 documentation-related pull requests (PRs) authored by AI agents and human developers, where documentation PRs are those that create or modify project documentation artifacts. We find that AI agents submit substantially more documentation-related PRs than humans in the studied repositories. We further observe that agent-authored documentation edits are typically integrated with little follow-up modification from humans, raising concerns about review practices and the reliability of agent-generated documentation. Overall, while AI agents already contribute substantially to documentation workflows, our results suggest concerns for emerging challenges for documentation quality assurance and human-AI collaboration in SE3.0.
Where Accountability Lives: Mapping Human Responsibility to Workflow Artifacts in Agentic Software Development
School of Architecture, Computing and Engineering, University of East London（伦敦东大学建筑、计算与工程学院）；School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast（贝尔法斯特女王大学电子、电气工程与计算机科学学院）
